Learning Deep Features for One-Class Classification

Abstract

We propose a deep learning-based solution for the problem of feature learning in one-class classification. The proposed method operates on top of a Convolutional Neural Network (CNN) of choice and produces descriptive features while maintaining a low intra-class variance in the feature space for the given class. For this purpose two loss functions, compactness loss and descriptiveness loss are proposed along with a parallel CNN architecture. A template matching-based framework is introduced to facilitate the testing process. Extensive experiments on publicly available anomaly detection, novelty detection and mobile active authentication datasets show that the proposed Deep One-Class (DOC) classification method achieves significant improvements over the state-of-the-art.

Accepted to appear in Transactions in Image Processing

References in corpus (1)

• One-Class Convolutional Neural Network

Cited by in corpus (15)

• A Unifying Review of Deep and Shallow Anomaly Detection
• Reliable Tuberculosis Detection using Chest X-ray with Deep Learning, Segmentation and Visualization
• Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detection
• DFR: Deep Feature Reconstruction for Unsupervised Anomaly Segmentation
• Deep Graph-level Anomaly Detection by Glocal Knowledge Distillation
• Image-Based Feature Representation for Insider Threat Classification
• Unsupervised Outlier Detection using Memory and Contrastive Learning
• Dense outlier detection and open-set recognition based on training with noisy negative images
• Learning image representations for anomaly detection: application to discovery of histological alterations in drug development
• Why do Angular Margin Losses work well for Semi-Supervised Anomalous Sound Detection?
• VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localization
• SAFE-OCC: A Novelty Detection Framework for Convolutional Neural Network Sensors and its Application in Process Control
• The OCON model: an old but green solution for distributable supervised classification for acoustic monitoring in smart cities
• Multi-representations Space Separation based Graph-level Anomaly-aware Detection
• The OCON model: an old but gold solution for distributable supervised classification